Visual Localization
Visual localization aims to determine a camera's position and orientation within a known environment using only visual information, eliminating the need for GPS or other external sensors. Current research focuses on improving accuracy and efficiency through various approaches, including leveraging deep learning models like neural radiance fields (NeRFs) for scene representation and pose estimation, and employing techniques such as image retrieval, keypoint matching, and fusion of global and local descriptors. These advancements are crucial for applications like autonomous navigation (especially in GPS-denied environments), augmented reality, and robotics, offering robust and scalable solutions for precise localization in diverse settings.
Papers
FUSELOC: Fusing Global and Local Descriptors to Disambiguate 2D-3D Matching in Visual Localization
Son Tung Nguyen, Alejandro Fontan, Michael Milford, Tobias Fischer
Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework
Xiao Han, Chen Zhu, Xiangyu Zhao, Hengshu Zhu